Role & seniority
- Data & (Gen)AI Architect / ML Engineer (seniority not explicitly stated)
- Own architecture roadmaps and collaborate with Enterprise Architects and C-level stakeholders
Stack/tools (from text)
- ML/DL: CNN, RNN, LSTM; event detection & classification
- Computer vision for DAS: spectrogram-based models, spatial/temporal pattern detection
- Data workflows: collecting, labeling, analyzing sensor/event data
- AI engineering lifecycle: testing, deployment, maintenance, automation
- Mentions automation/experiments, code/algorithm review & optimization
- (No specific programming/cloud tools named)
Top 3 responsibilities
- Design & implement Data and (Gen)AI architectures, including AI software/hardware integration and roadmaps
- Build ML/DL pipelines for event detection/classification (data collection/labeling, training, evaluation, experimentation)
- Assess data quality/source effectiveness and develop automation methods to speed up labeling and improve gathering techniques
Must-have skills
- ML/DL for event detection/classification (CNN and sequential models like LSTM/RNN)
- Data engineering for labeling/experimentation and evaluation of data sources
- AI testing, deployment, and maintenance best practices
- Ability to optimize algorithms/code and create training/evaluation frameworks
- Strong understanding of fiber sensor/DAS event data and signal-to-vision approaches (spectrograms)
Nice-to-haves

Full Description

Role description

Role Purpose: Key Accountabilities: Preferred Experience and Qualification

Other details

Driven by innovation, design, plan and implement Data & (Gen)AI architectures including the associated roadmaps, where you work together with Enterprise Architects and Senior Management up to C-Level on the customer side

Design and set up experiments for collecting, labeling analyzing data of different kinds of events from fiber based sensor solutions

Assess the effectiveness and accuracy of data sources and data gathering techniques

Develop automation methods for faster labeling of collected data

Create architectural approaches for AI software and hardware integration

Define AI solution objectives and ensure alignment with business outcomes

Implement best practices for AI testing, deployment, and maintenance

Develop Machine Learning and Deep Learning methods for event detection and classification

Develop efficient frameworks for training and evaluating the event detection/classification models

Track the innovations in AI/ML technologies and algorithms/processing/ computation and its implementation to develop next generation fiber sensing solution

Review and Optimize existing code/algorithm

Create systematic plans to run the experiments to fine-tune the event detection/classification models

Plan the tasks and provide estimates and timelines

Support marketing/sales team with application notes, white papers and presentations

Contribute to simulation model development and data analysis of various sensor solutions

Design, Develop and optimize CNN-based models for event detection and classification using spectrograms and other signal-derived image formats.

Apply computer vision techniques to identify spatial and temporal patterns in DAS data visualizations.

Use deep learning architectures (e.g., CNN, RNN, LSTM) to model sequential and spatial aspects.

QA Lead

Full Description

Role Purpose: Key Accountabilities: Preferred Experience and Qualification